Georgios Petrakis

Papers

Total Citations

H-Index

About

Georgios Petrakis is a researcher at the forefront of planetary robotics and autonomous navigation, with a primary focus on applying deep learning to unstructured, extraterrestrial environments. His most impactful work centers on lunar ground segmentation, where he developed a modified U-Net neural network to enable planetary rovers to intelligently interpret their surroundings. This contribution, published in 2024 and already garnering 9 citations, addresses a critical challenge in space exploration: providing robotic systems with the perceptual awareness needed to safely traverse alien terrains. By adapting state-of-the-art computer vision architectures for planetary-like settings, Petrakis bridges the gap between terrestrial AI and the harsh realities of lunar and Martian landscapes. His research not only advances scene understanding for autonomous rovers but also lays groundwork for future missions where reliable, real-time terrain classification is essential for navigation and scientific discovery. As his work gains traction in the space robotics community, Petrakis is establishing himself as a key contributor to the next generation of intelligent planetary explorers.